Coverage for biobb_analysis/gromacs/gmx_cluster.py: 77%
86 statements
« prev ^ index » next coverage.py v7.6.4, created at 2024-11-14 14:38 +0000
1#!/usr/bin/env python3
3"""Module containing the GMX Cluster class and the command line interface."""
4import argparse
5from typing import Optional
6from biobb_common.generic.biobb_object import BiobbObject
7from biobb_common.configuration import settings
8from biobb_common.tools import file_utils as fu
9from biobb_common.tools.file_utils import launchlogger
10from biobb_analysis.gromacs.common import check_input_path, check_traj_path, check_index_path, check_out_pdb_path, get_binary_path, get_image_selection, get_selection_index_file, get_dista, get_method, get_cutoff
13class GMXCluster(BiobbObject):
14 """
15 | biobb_analysis GMXCluster
16 | Wrapper of the GROMACS cluster module for clustering structures from a given GROMACS compatible trajectory.
17 | `GROMACS cluster <http://manual.gromacs.org/current/onlinehelp/gmx-cluster.html>`_ can cluster structures using several different methods. Distances between structures can be determined from a trajectory. RMS deviation after fitting or RMS deviation of atom-pair distances can be used to define the distance between structures.
19 Args:
20 input_structure_path (str): Path to the input structure file. File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/gromacs/topology.tpr>`_. Accepted formats: tpr (edam:format_2333), gro (edam:format_2033), g96 (edam:format_2033), pdb (edam:format_1476), brk (edam:format_2033), ent (edam:format_1476).
21 input_traj_path (str): Path to the GROMACS trajectory file. File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/gromacs/trajectory.trr>`_. Accepted formats: xtc (edam:format_3875), trr (edam:format_3910), cpt (edam:format_2333), gro (edam:format_2033), g96 (edam:format_2033), pdb (edam:format_1476), tng (edam:format_3876).
22 input_index_path (str) (Optional): Path to the GROMACS index file. File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/gromacs/index.ndx>`_. Accepted formats: ndx (edam:format_2033).
23 output_pdb_path (str): Path to the output cluster file. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/gromacs/ref_cluster.pdb>`_. Accepted formats: xtc (edam:format_3875), trr (edam:format_3910), cpt (edam:format_2333), gro (edam:format_2033), g96 (edam:format_2033), pdb (edam:format_1476), tng (edam:format_3876).
24 output_cluster_log_path (str) (Optional): Path to the output log file. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/gmx_cluster_cluster.log>`_. Accepted formats: log (edam:format_2330).
25 output_rmsd_cluster_xpm_path (str) (Optional):Path to the output X PixMap compatible matrix file. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/gmx_cluster_rmsd-clust.xpm>`_. Accepted formats: xpm (edam:format_3599).
26 output_rmsd_dist_xvg_path (str) (Optional): Path to xvgr/xmgr file. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/gmx_cluster_rmsd-dist.xvg>`_. Accepted formats: xvg (edam:format_2330).
27 properties (dic - Python dictionary object containing the tool parameters, not input/output files):
28 * **fit_selection** (*str*) - ("System") Group where the fitting will be performed. If **input_index_path** provided, check the file for the accepted values. Values: System (all atoms in the system), Protein (all protein atoms), Protein-H (protein atoms excluding hydrogens), C-alpha (C-alpha atoms), Backbone (protein backbone atoms: N; C-alpha and C), MainChain (protein main chain atoms: N; C-alpha; C and O; including oxygens in C-terminus), MainChain+Cb (protein main chain atoms including C-beta), MainChain+H (protein main chain atoms including backbone amide hydrogens and hydrogens on the N-terminus), SideChain (protein side chain atoms: that is all atoms except N; C-alpha; C; O; backbone amide hydrogens and oxygens in C-terminus and hydrogens on the N-terminus), SideChain-H (protein side chain atoms excluding all hydrogens), Prot-Masses (protein atoms excluding dummy masses), non-Protein (all non-protein atoms), Water (water molecules), SOL (water molecules), non-Water (anything not covered by the Water group), Ion (any name matching an Ion entry in residuetypes.dat), NA (all NA atoms), CL (all CL atoms), Water_and_ions (combination of the Water and Ions groups).
29 * **output_selection** (*str*) - ("System") Group that is going to be written in the output trajectory. If **input_index_path** provided, check the file for the accepted values. Values: System (all atoms in the system), Protein (all protein atoms), Protein-H (protein atoms excluding hydrogens), C-alpha (C-alpha atoms), Backbone (protein backbone atoms: N; C-alpha and C), MainChain (protein main chain atoms: N; C-alpha; C and O; including oxygens in C-terminus), MainChain+Cb (protein main chain atoms including C-beta), MainChain+H (protein main chain atoms including backbone amide hydrogens and hydrogens on the N-terminus), SideChain (protein side chain atoms: that is all atoms except N; C-alpha; C; O; backbone amide hydrogens and oxygens in C-terminus and hydrogens on the N-terminus), SideChain-H (protein side chain atoms excluding all hydrogens), Prot-Masses (protein atoms excluding dummy masses), non-Protein (all non-protein atoms), Water (water molecules), SOL (water molecules), non-Water (anything not covered by the Water group), Ion (any name matching an Ion entry in residuetypes.dat), NA (all NA atoms), CL (all CL atoms), Water_and_ions (combination of the Water and Ions groups).
30 * **dista** (*bool*) - (False) Use RMSD of distances instead of RMS deviation.
31 * **nofit** (*bool*) - (False) Do not use least squares fitting before RMSD calculation.
32 * **method** (*str*) - ("linkage") Method for cluster determination. Values: linkage (Add a structure to a cluster when its distance to any element of the cluster is less than cutoff), jarvis-patrick (Add a structure to a cluster when this structure and a structure in the cluster have each other as neighbors and they have a least P neighbors in common), monte-carlo (Reorder the RMSD matrix using Monte Carlo such that the order of the frames is using the smallest possible increments), diagonalization (Diagonalize the RMSD matrix), gromos (Count number of neighbors using cut-off and take structure with largest number of neighbors with all its neighbors as cluster and eliminate it from the pool of clusters).
33 * **cutoff** (*float*) - (0.1) [0~10|0.1] RMSD cut-off (nm) for two structures to be neighbor.
34 * **binary_path** (*str*) - ("gmx") Path to the GROMACS executable binary.
35 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
36 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
37 * **sandbox_path** (*str*) - ("./") [WF property] Parent path to the sandbox directory.
38 * **container_path** (*str*) - (None) Container path definition.
39 * **container_image** (*str*) - ('gromacs/gromacs:2022.2') Container image definition.
40 * **container_volume_path** (*str*) - ('/tmp') Container volume path definition.
41 * **container_working_dir** (*str*) - (None) Container working directory definition.
42 * **container_user_id** (*str*) - (None) Container user_id definition.
43 * **container_shell_path** (*str*) - ('/bin/bash') Path to default shell inside the container.
45 Examples:
46 This is a use example of how to use the building block from Python::
48 from biobb_analysis.gromacs.gmx_cluster import gmx_cluster
49 prop = {
50 'fit_selection': 'System',
51 'output_selection': 'System',
52 'method': 'linkage'
53 }
54 gmx_cluster(input_structure_path='/path/to/myStructure.tpr',
55 input_traj_path='/path/to/myTrajectory.trr',
56 input_index_path='/path/to/myIndex.ndx',
57 output_pdb_path='/path/to/newStructure.pdb',
58 properties=prop)
60 Info:
61 * wrapped_software:
62 * name: GROMACS cluster
63 * version: >=2019.1
64 * license: LGPL 2.1
65 * ontology:
66 * name: EDAM
67 * schema: http://edamontology.org/EDAM.owl
69 """
71 def __init__(self, input_structure_path, input_traj_path, output_pdb_path,
72 input_index_path=None, output_cluster_log_path=None, output_rmsd_cluster_xpm_path=None,
73 output_rmsd_dist_xvg_path=None, properties=None, **kwargs) -> None:
74 properties = properties or {}
76 # Call parent class constructor
77 super().__init__(properties)
78 self.locals_var_dict = locals().copy()
80 # Input/Output files
81 self.io_dict = {
82 "in": {"input_structure_path": input_structure_path, "input_traj_path": input_traj_path, "input_index_path": input_index_path},
83 "out": {"output_pdb_path": output_pdb_path, "output_cluster_log_path": output_cluster_log_path,
84 "output_rmsd_cluster_xpm_path": output_rmsd_cluster_xpm_path, "output_rmsd_dist_xvg_path": output_rmsd_dist_xvg_path}
85 }
87 # Properties specific for BB
88 self.fit_selection = properties.get('fit_selection', "System")
89 self.output_selection = properties.get('output_selection', "System")
90 self.method = properties.get('method', "linkage")
91 self.dista = properties.get('dista', False)
92 self.nofit = properties.get('nofit', False)
93 self.cutoff = properties.get('cutoff', 0.1)
94 self.properties = properties
96 # Properties common in all GROMACS BB
97 self.binary_path = get_binary_path(properties, 'binary_path')
99 # Check the properties
100 self.check_properties(properties)
101 self.check_arguments()
103 def check_data_params(self, out_log, err_log):
104 """ Checks all the input/output paths and parameters """
105 self.io_dict["in"]["input_structure_path"] = check_input_path(self.io_dict["in"]["input_structure_path"], out_log, self.__class__.__name__)
106 self.io_dict["in"]["input_traj_path"] = check_traj_path(self.io_dict["in"]["input_traj_path"], out_log, self.__class__.__name__)
107 self.io_dict["in"]["input_index_path"] = check_index_path(self.io_dict["in"]["input_index_path"], out_log, self.__class__.__name__)
108 self.io_dict["out"]["output_pdb_path"] = check_out_pdb_path(self.io_dict["out"]["output_pdb_path"], out_log, self.__class__.__name__)
109 if not self.io_dict["in"]["input_index_path"]:
110 self.fit_selection = get_image_selection(self.properties, 'fit_selection', out_log, self.__class__.__name__)
111 self.output_selection = get_image_selection(self.properties, 'output_selection', out_log, self.__class__.__name__)
112 else:
113 self.fit_selection = get_selection_index_file(self.properties, self.io_dict["in"]["input_index_path"], 'fit_selection', out_log, self.__class__.__name__)
114 self.output_selection = get_selection_index_file(self.properties, self.io_dict["in"]["input_index_path"], 'output_selection', out_log, self.__class__.__name__)
115 self.dista = get_dista(self.properties, out_log, self.__class__.__name__)
116 self.method = get_method(self.properties, out_log, self.__class__.__name__)
117 self.cutoff = get_cutoff(self.properties, out_log, self.__class__.__name__)
119 @launchlogger
120 def launch(self) -> int:
121 """Execute the :class:`GMXCluster <gromacs.gmx_cluster.GMXCluster>` gromacs.gmx_cluster.GMXCluster object."""
123 # check input/output paths and parameters
124 self.check_data_params(self.out_log, self.err_log)
126 # Optional output files
127 if not self.io_dict['out'].get('output_rmsd_dist_xvg_path'):
128 self.io_dict['out']['output_rmsd_dist_xvg_path'] = fu.create_name(prefix=self.prefix, step=self.step, name='rmsd-dist.xvg')
129 self.tmp_files.append(self.io_dict['out']['output_rmsd_dist_xvg_path'])
130 if not self.io_dict['out'].get('output_rmsd_cluster_xpm_path'):
131 self.io_dict['out']['output_rmsd_cluster_xpm_path'] = fu.create_name(prefix=self.prefix, step=self.step, name='rmsd-clust.xpm')
132 self.tmp_files.append(self.io_dict['out']['output_rmsd_cluster_xpm_path'])
133 if not self.io_dict['out'].get('output_cluster_log_path'):
134 self.io_dict['out']['output_cluster_log_path'] = fu.create_name(prefix=self.prefix, step=self.step, name='cluster.log')
135 self.tmp_files.append(self.io_dict['out']['output_cluster_log_path'])
137 # Setup Biobb
138 if self.check_restart():
139 return 0
141 # standard input
142 self.io_dict['in']['stdin_file_path'] = fu.create_stdin_file(f'{self.fit_selection} {self.output_selection}')
143 self.stage_files()
145 self.cmd = [self.binary_path, 'cluster',
146 '-g', self.stage_io_dict['out']['output_cluster_log_path'],
147 '-dist', self.stage_io_dict['out']['output_rmsd_dist_xvg_path'],
148 '-o', self.stage_io_dict['out']['output_rmsd_cluster_xpm_path'],
149 '-s', self.stage_io_dict["in"]["input_structure_path"],
150 '-f', self.stage_io_dict["in"]["input_traj_path"],
151 '-cl', self.stage_io_dict["out"]["output_pdb_path"],
152 '-cutoff', str(self.cutoff),
153 '-method', self.method]
155 if self.stage_io_dict["in"].get("input_index_path"):
156 self.cmd.extend(['-n', self.stage_io_dict["in"]["input_index_path"]])
158 if self.dista:
159 self.cmd.append('-dista')
161 if self.nofit:
162 self.cmd.append('-nofit')
164 # Add stdin input file
165 self.cmd.append('<')
166 self.cmd.append(self.stage_io_dict["in"]["stdin_file_path"])
168 # Run Biobb block
169 self.run_biobb()
171 # Copy files to host
172 self.copy_to_host()
174 self.tmp_files.extend([
175 self.stage_io_dict.get("unique_dir", ""),
176 self.io_dict['in'].get("stdin_file_path", ""),
177 ])
178 self.remove_tmp_files()
180 self.check_arguments(output_files_created=True, raise_exception=False)
182 return self.return_code
185def gmx_cluster(input_structure_path: str, input_traj_path: str, output_pdb_path: str, input_index_path: Optional[str] = None, output_cluster_log_path: Optional[str] = None,
186 output_rmsd_cluster_xpm_path: Optional[str] = None, output_rmsd_dist_xvg_path: Optional[str] = None, properties: Optional[dict] = None, **kwargs) -> int:
187 """Execute the :class:`GMXCluster <gromacs.gmx_cluster.GMXCluster>` class and
188 execute the :meth:`launch() <gromacs.gmx_cluster.GMXCluster.launch>` method."""
190 return GMXCluster(input_structure_path=input_structure_path,
191 input_traj_path=input_traj_path,
192 output_pdb_path=output_pdb_path,
193 input_index_path=input_index_path,
194 output_cluster_log_path=output_cluster_log_path,
195 output_rmsd_cluster_xpm_path=output_rmsd_cluster_xpm_path,
196 output_rmsd_dist_xvg_path=output_rmsd_dist_xvg_path,
197 properties=properties, **kwargs).launch()
200def main():
201 """Command line execution of this building block. Please check the command line documentation."""
202 parser = argparse.ArgumentParser(description="Creates cluster structures from a given GROMACS compatible trajectory.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999))
203 parser.add_argument('--config', required=False, help='Configuration file')
205 # Specific args of each building block
206 required_args = parser.add_argument_group('required arguments')
207 required_args.add_argument('--input_structure_path', required=True, help='Path to the input structure file. Accepted formats: tpr, gro, g96, pdb, brk, ent.')
208 required_args.add_argument('--input_traj_path', required=True, help='Path to the GROMACS trajectory file. Accepted formats: xtc, trr, cpt, gro, g96, pdb, tng.')
209 parser.add_argument('--input_index_path', required=False, help="Path to the GROMACS index file. Accepted formats: ndx.")
210 required_args.add_argument('--output_pdb_path', required=True, help='Path to the output cluster file. Accepted formats: xtc, trr, cpt, gro, g96, pdb, tng.')
211 parser.add_argument('--output_cluster_log_path', required=False, help='Path to the output log file. Accepted formats: log.')
212 parser.add_argument('--output_rmsd_cluster_xpm_path', required=False, help='Path to the output xpm file. Accepted formats: xpm.')
213 parser.add_argument('--output_rmsd_dist_xvg_path', required=False, help='Path to the output xvg file. Accepted formats: xvg.')
215 args = parser.parse_args()
216 args.config = args.config or "{}"
217 properties = settings.ConfReader(config=args.config).get_prop_dic()
219 # Specific call of each building block
220 gmx_cluster(input_structure_path=args.input_structure_path,
221 input_traj_path=args.input_traj_path,
222 output_pdb_path=args.output_pdb_path,
223 input_index_path=args.input_index_path,
224 output_cluster_log_path=args.output_cluster_log_path,
225 output_rmsd_cluster_xpm_path=args.output_rmsd_cluster_xpm_path,
226 output_rmsd_dist_xvg_path=args.output_rmsd_dist_xvg_path,
227 properties=properties)
230if __name__ == '__main__':
231 main()